MAXIMUM LIKELIHOOD CLASSIFICATION
Maximum likelihood Classification is a statistical decision criterion to assist in the classification of overlapping signatures; pixels are assigned to the class of highest probability.
In Maximum Likelihood Classification, besides determining the means and covariances for the classes that fall within the training sites, a statistical (Bayesian) Probability Function is also calculated for the class data. The class DN distribution for a two-dimensional case, gives rise to elliptical boundaries which define the equiprobability envelope for each class. Fig 1 is a scatter plot that shows the outer envelope bounding each class.
There are contours inside each ellipse that indicate the degree of probability. Associated with each ellipse is a separate function that expresses a statistical surface (bell-shaped in three dimensions) called probability density function. Using this function, the likelihood of each unknown pixel in belonging to one or the other ellipse is determined. The Bayesian Classifier assesses the likely occurrence of each class (common to rare) and assigns the pixel to the class to which it most likely belongs.
The maximum likelihood classifier is considered to give more accurate results than parallelepiped classification. However it is much slower due to extra computations. We put the word `accurate' in quotes because this assumes that classes in the input data have a Gaussian distribution and that signatures were well selected; this is not always a safe assumption.
We made this Supervised Classification of landcover of the area around Askot, Kumaon Himalaya using the Maximum Likelihood classifier acting on all seven bands of Landsat ETM+ multispectral data (Fig 2). Multiband classes are derived statistically and each unknown pixel is assigned to a class using the maximum likelihood method.
This website is hosted by
Department of Geology
Aligarh Muslim University, Aligarh - 202 002 (India)